no code implementations • 6 Jul 2017 • Ayush Jaiswal, Ekraam Sabir, Wael Abd-Almageed, Premkumar Natarajan
In this paper, we present a novel deep learning-based approach for assessing the semantic integrity of multimedia packages containing images and captions, using a reference set of multimedia packages.
no code implementations • 20 Nov 2017 • Ayush Jaiswal, Wael Abd-Almageed, Yue Wu, Premkumar Natarajan
Conditional Generative Adversarial Networks (cGANs) are generative models that can produce data samples ($x$) conditioned on both latent variables ($z$) and known auxiliary information ($c$).
1 code implementation • 17 Feb 2018 • Ayush Jaiswal, Wael Abd-Almageed, Yue Wu, Premkumar Natarajan
We provide guidelines for designing CapsNet discriminators and the updated GAN objective function, which incorporates the CapsNet margin loss, for training CapsuleGAN models.
no code implementations • 2 May 2018 • Ayush Jaiswal, Dong Guo, Cauligi S. Raghavendra, Paul Thompson
Machine Learning (ML) is increasingly being used for computer aided diagnosis of brain related disorders based on structural magnetic resonance imaging (MRI) data.
no code implementations • NeurIPS 2018 • Ayush Jaiswal, Yue Wu, Wael Abd-Almageed, Premkumar Natarajan
Data representations that contain all the information about target variables but are invariant to nuisance factors benefit supervised learning algorithms by preventing them from learning associations between these factors and the targets, thus reducing overfitting.
1 code implementation • CVPR 2019 • Ayush Jaiswal, Yue Wu, Wael Abd-Almageed, Iacopo Masi, Premkumar Natarajan
Image repurposing is a commonly used method for spreading misinformation on social media and online forums, which involves publishing untampered images with modified metadata to create rumors and further propaganda.
no code implementations • 8 Mar 2019 • Ayush Jaiswal, Shuai Xia, Iacopo Masi, Wael Abd-Almageed
For enterprise, personal and societal applications, there is now an increasing demand for automated authentication of identity from images using computer vision.
1 code implementation • 2 May 2019 • Ekraam Sabir, Jiaxin Cheng, Ayush Jaiswal, Wael Abd-Almageed, Iacopo Masi, Prem Natarajan
The spread of misinformation through synthetically generated yet realistic images and videos has become a significant problem, calling for robust manipulation detection methods.
no code implementations • 7 May 2019 • Ayush Jaiswal, Yue Wu, Wael Abd-Almageed, Premkumar Natarajan
We present a unified invariance framework for supervised neural networks that can induce independence to nuisance factors of data without using any nuisance annotations, but can additionally use labeled information about biasing factors to force their removal from the latent embedding for making fair predictions.
1 code implementation • 7 Jul 2019 • I-Hung Hsu, Ayush Jaiswal, Premkumar Natarajan
Deep neural network models for speech recognition have achieved great success recently, but they can learn incorrect associations between the target and nuisance factors of speech (e. g., speaker identities, background noise, etc.
no code implementations • 11 Nov 2019 • Ayush Jaiswal, Daniel Moyer, Greg Ver Steeg, Wael Abd-Almageed, Premkumar Natarajan
We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechanism.
no code implementations • 2 Dec 2019 • Ayush Jaiswal, Rob Brekelmans, Daniel Moyer, Greg Ver Steeg, Wael Abd-Almageed, Premkumar Natarajan
Supervised machine learning models often associate irrelevant nuisance factors with the prediction target, which hurts generalization.
no code implementations • 5 Jul 2020 • Xiao Guo, Hengameh Mirzaalian, Ekraam Sabir, Ayush Jaiswal, Wael Abd-Almageed
To overcome this gap, we introduce CORD19STS dataset which includes 13, 710 annotated sentence pairs collected from COVID-19 open research dataset (CORD-19) challenge.
no code implementations • 23 Nov 2020 • Ekraam Sabir, Ayush Jaiswal, Wael AbdAlmageed, Prem Natarajan
The problem setup requires algorithms to perform multimodal semantic forensics to authenticate a query multimedia package using a reference dataset of potentially related packages as evidences.
no code implementations • 28 Nov 2020 • Ayush Jaiswal, Yue Wu, Pradeep Natarajan, Premkumar Natarajan
Finally, we propose (1) baseline methods and (2) a new adversarial learning framework for class-agnostic detection that forces the model to exclude class-specific information from features used for predictions.
Ranked #100 on Image Classification on ObjectNet (using extra training data)
1 code implementation • CVPR 2021 • Jiaxin Cheng, Ayush Jaiswal, Yue Wu, Pradeep Natarajan, Prem Natarajan
Neural Style Transfer (NST) has quickly evolved from single-style to infinite-style models, also known as Arbitrary Style Transfer (AST).
no code implementations • CVPR 2022 • Sonam Goenka, Zhaoheng Zheng, Ayush Jaiswal, Rakesh Chada, Yue Wu, Varsha Hedau, Pradeep Natarajan
Fashion image retrieval based on a query pair of reference image and natural language feedback is a challenging task that requires models to assess fashion related information from visual and textual modalities simultaneously.
no code implementations • ICCV 2023 • Anwesan Pal, Sahil Wadhwa, Ayush Jaiswal, Xu Zhang, Yue Wu, Rakesh Chada, Pradeep Natarajan, Henrik I. Christensen
Extensive evaluation results show that our proposed method outperforms the previous state-of-the-art algorithm by 50. 5%, on Multi-turn FashionIQ -- the only existing multi-turn fashion dataset currently, in addition to having a relative improvement of 12. 6% on Multi-turn Shoes -- an extension of the single-turn Shoes dataset that we created in this work.